feat(review): 取证层多源化 + 视觉多图（整体+2x2 象限）

- 新增 evidence_model.py：统一证据模型（source_type + images 列表），访问器兼容旧 image_b64/image_mime 单图字段
- phases/evidence.py：新增 collect() 多源分发 seam（仅 CAD）、capture_images() 整体+等分象限多图（结束复位视口）、sub_windows()
- phases/review.py：多图逐张下采样喂 LLM，payload 增加 source_type
- config.py：EVIDENCE_DETAIL_TILES=4 / EVIDENCE_MAX_IMAGES=5（默认开启多图）
- 新增 tests/test_evidence_model.py，更新 evidence/review 断言与 fakes 归一

dwg_review/__main__.py

@@ -11,6 +11,7 @@ from . import findings as findings_mod
 from .annotator import annotate, clear
 from .checklist import build_system_prompt, checklist_summary
 from .context import ReviewContext
+from .evidence_model import evidence_images
 from .mcp_client import McpError, McpToolError, result_json
 from .phases import evidence as evidence_phase
 from .phases import planning, report, review
@@ -20,7 +21,8 @@ def _dump_evidence(evidences):
     out_dir = Path(config.REPORT_DIR)
     out_dir.mkdir(parents=True, exist_ok=True)
     path = out_dir / "evidence.json"
-    trimmed = [{k: v for k, v in e.items() if k != "image_b64"} for e in evidences]
+    drop = ("images", "image_b64", "image_mime")
+    trimmed = [{k: v for k, v in e.items() if k not in drop} for e in evidences]
     path.write_text(json.dumps(trimmed, ensure_ascii=False, indent=2), encoding="utf-8")
     return path
 
@@ -67,14 +69,14 @@ def run_review(ctx, args):
             f"  - 图框 {idx}/{len(frames)} kind={frame.get('kind')} "
             f"sheet={frame.get('sheet_size')}"
         )
-        ev = evidence_phase.collect_frame(ctx, idx, frame)
+        ev = evidence_phase.collect(ctx, idx, frame)
         if ev is None:
             print("    [跳过] 缺少有效包围盒")
             continue
         evidences.append(ev)
         print(
             f"    图元 {(ev.get('entities') or {}).get('total')} 条，"
-            f"截图 {'有' if ev.get('image_b64') else '无'}"
+            f"截图 {len(evidence_images(ev))} 张"
         )
 
     if args.plan_only: